{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UNVGDDDL3OYK5YZZZNEKQU5OGE","short_pith_number":"pith:UNVGDDDL","schema_version":"1.0","canonical_sha256":"a36a618c6bdbb0aee339cb48a853ae310d838cdad3afda787a2c228dc30ed9f5","source":{"kind":"arxiv","id":"2204.01571","version":1},"attestation_state":"computed","paper":{"title":"Coarse-to-Fine Q-attention with Learned Path Ranking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Pieter Abbeel, Stephen James","submitted_at":"2022-04-04T15:23:14Z","abstract_excerpt":"We propose Learned Path Ranking (LPR), a method that accepts an end-effector goal pose, and learns to rank a set of goal-reaching paths generated from an array of path generating methods, including: path planning, Bezier curve sampling, and a learned policy. The core idea being that each of the path generation modules will be useful in different tasks, or at different stages in a task. When LPR is added as an extension to C2F-ARM, our new system, C2F-ARM+LPR, retains the sample efficiency of its predecessor, while also being able to accomplish a larger set of tasks; in particular, tasks that r"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2204.01571","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-04-04T15:23:14Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"d0124bedd990d686a7d7ffbdd3555417c0b55f7fb7ba3d152159232266aa39e7","abstract_canon_sha256":"8cd54f6b9fce644a7a40ce65c6d1463e3438cf2b1d5c2edb5092d8f300a6b58a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:20.401212Z","signature_b64":"0tdlSzaZF7t1ho7HzZ54i786ZSFi6g31O4VWW3kJMQYR15t4NPZq8xEWfqhGfE6I2oxnvoNMFfk2dE4av5UIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a36a618c6bdbb0aee339cb48a853ae310d838cdad3afda787a2c228dc30ed9f5","last_reissued_at":"2026-07-05T04:11:20.400760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:20.400760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Coarse-to-Fine Q-attention with Learned Path Ranking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Pieter Abbeel, Stephen James","submitted_at":"2022-04-04T15:23:14Z","abstract_excerpt":"We propose Learned Path Ranking (LPR), a method that accepts an end-effector goal pose, and learns to rank a set of goal-reaching paths generated from an array of path generating methods, including: path planning, Bezier curve sampling, and a learned policy. The core idea being that each of the path generation modules will be useful in different tasks, or at different stages in a task. When LPR is added as an extension to C2F-ARM, our new system, C2F-ARM+LPR, retains the sample efficiency of its predecessor, while also being able to accomplish a larger set of tasks; in particular, tasks that r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.01571","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2204.01571/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2204.01571","created_at":"2026-07-05T04:11:20.400816+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.01571v1","created_at":"2026-07-05T04:11:20.400816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.01571","created_at":"2026-07-05T04:11:20.400816+00:00"},{"alias_kind":"pith_short_12","alias_value":"UNVGDDDL3OYK","created_at":"2026-07-05T04:11:20.400816+00:00"},{"alias_kind":"pith_short_16","alias_value":"UNVGDDDL3OYK5YZZ","created_at":"2026-07-05T04:11:20.400816+00:00"},{"alias_kind":"pith_short_8","alias_value":"UNVGDDDL","created_at":"2026-07-05T04:11:20.400816+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06564","citing_title":"Lift3D-VLA: Lifting VLA Models to 3D Geometry and Dynamics-Aware Manipulation","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23589","citing_title":"KEMO: Event-Driven Keyframe Memory for Long-Horizon Robot Manipulation with VLA Policies","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15536","citing_title":"SkiP: When to Skip and When to Refine for Efficient Robot Manipulation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10921","citing_title":"RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UNVGDDDL3OYK5YZZZNEKQU5OGE","json":"https://pith.science/pith/UNVGDDDL3OYK5YZZZNEKQU5OGE.json","graph_json":"https://pith.science/api/pith-number/UNVGDDDL3OYK5YZZZNEKQU5OGE/graph.json","events_json":"https://pith.science/api/pith-number/UNVGDDDL3OYK5YZZZNEKQU5OGE/events.json","paper":"https://pith.science/paper/UNVGDDDL"},"agent_actions":{"view_html":"https://pith.science/pith/UNVGDDDL3OYK5YZZZNEKQU5OGE","download_json":"https://pith.science/pith/UNVGDDDL3OYK5YZZZNEKQU5OGE.json","view_paper":"https://pith.science/paper/UNVGDDDL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.01571&json=true","fetch_graph":"https://pith.science/api/pith-number/UNVGDDDL3OYK5YZZZNEKQU5OGE/graph.json","fetch_events":"https://pith.science/api/pith-number/UNVGDDDL3OYK5YZZZNEKQU5OGE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UNVGDDDL3OYK5YZZZNEKQU5OGE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UNVGDDDL3OYK5YZZZNEKQU5OGE/action/storage_attestation","attest_author":"https://pith.science/pith/UNVGDDDL3OYK5YZZZNEKQU5OGE/action/author_attestation","sign_citation":"https://pith.science/pith/UNVGDDDL3OYK5YZZZNEKQU5OGE/action/citation_signature","submit_replication":"https://pith.science/pith/UNVGDDDL3OYK5YZZZNEKQU5OGE/action/replication_record"}},"created_at":"2026-07-05T04:11:20.400816+00:00","updated_at":"2026-07-05T04:11:20.400816+00:00"}